Merge branch 'xinnan-tech:main' into main

main/xiaozhi-server/core/handle/functionHandler.py

@@ -1,16 +1,16 @@
-import asyncio
-from enum import Enum
-
 from config.logger import setup_logging
 import json
 from plugins_func.register import FunctionRegistry, ActionResponse, Action, ToolType
+from plugins_func.functions.hass_init import append_devices_to_prompt
+
 TAG = __name__
 logger = setup_logging()
 
 
 class FunctionHandler:
-    def __init__(self, config):
-        self.config = config
+    def __init__(self, conn):
+        self.conn = conn
+        self.config = conn.config
         self.function_registry = FunctionRegistry()
         self.register_nessary_functions()
         self.register_config_functions()
@@ -26,9 +26,10 @@ class FunctionHandler:
         func_names = ",".join(surport_plugins)
         for function_desc in self.functions_desc:
             if function_desc["function"]["name"] == "plugin_loader":
-                function_desc["function"]["description"] = function_desc["function"]["description"].replace("[plugins]", func_names)
+                function_desc["function"]["description"] = function_desc["function"]["description"].replace("[plugins]",
+                                                                                                            func_names)
                 break
-        
+
     def upload_functions_desc(self):
         self.functions_desc = self.function_registry.get_all_function_desc()
 
@@ -47,7 +48,6 @@ class FunctionHandler:
     def register_nessary_functions(self):
         """注册必要的函数"""
         self.function_registry.register_function("handle_exit_intent")
-        self.function_registry.register_function("play_music")
         self.function_registry.register_function("plugin_loader")
         self.function_registry.register_function("get_time")
         self.function_registry.register_function("raise_and_lower_the_volume")
@@ -57,6 +57,9 @@ class FunctionHandler:
         for func in self.config["Intent"]["function_call"].get("functions", []):
             self.function_registry.register_function(func)
 
+        """home assistant需要初始化提示词"""
+        append_devices_to_prompt(self.conn)
+
     def get_function(self, name):
         return self.function_registry.get_function(name)
 
@@ -81,4 +84,4 @@ class FunctionHandler:
         except Exception as e:
             logger.bind(tag=TAG).error(f"处理function call错误: {e}")
 
-        return None
+        return None

main/xiaozhi-server/core/handle/helloHandle.py

@@ -1,8 +1,72 @@
 import json
 from config.logger import setup_logging
+from core.handle.sendAudioHandle import send_stt_message
+from core.utils.util import remove_punctuation_and_length
+import shutil
+import asyncio
+import os
+import random
+import time
 
 logger = setup_logging()
 
+WAKEUP_CONFIG = {"dir": "config/assets/", "file_name": "wakeup_words", "create_time": time.time(), "refresh_time": 10,
+                 "words": ["很高兴见到你", "你好啊", "我们又见面了", "最近可好?", "很高兴再次和你谈话", "在干嘛"]}
+
 
 async def handleHelloMessage(conn):
     await conn.websocket.send(json.dumps(conn.welcome_msg))
+
+
+async def checkWakeupWords(conn, text):
+    enable_wakeup_words_response_cache = conn.config["enable_wakeup_words_response_cache"]
+    """是否开启唤醒词加速"""
+    if not enable_wakeup_words_response_cache:
+        return False
+    """检查是否是唤醒词"""
+    _, text = remove_punctuation_and_length(text)
+    if text in conn.config.get("wakeup_words"):
+        await send_stt_message(conn, text)
+        conn.tts_first_text_index = 0
+        conn.tts_last_text_index = 0
+        conn.llm_finish_task = True
+
+        file = getWakeupWordFile(WAKEUP_CONFIG["file_name"])
+        if file is None:
+            asyncio.create_task(wakeupWordsResponse(conn))
+            return False
+        opus_packets, duration = conn.tts.audio_to_opus_data(file)
+        conn.audio_play_queue.put((opus_packets, text, 0))
+        if time.time() - WAKEUP_CONFIG["create_time"] > WAKEUP_CONFIG["refresh_time"]:
+            asyncio.create_task(wakeupWordsResponse(conn))
+        return True
+    return False
+
+
+def getWakeupWordFile(file_name):
+    for file in os.listdir(WAKEUP_CONFIG["dir"]):
+        if "my_"+file_name in file:
+            return f"config/assets/{file}"
+
+    """查找config/assets/目录下名称为wakeup_words的文件"""
+    for file in os.listdir(WAKEUP_CONFIG["dir"]):
+        if file_name in file:
+            return f"config/assets/{file}"
+    return None
+
+
+async def wakeupWordsResponse(conn):
+    """唤醒词响应"""
+    wakeup_word = random.choice(WAKEUP_CONFIG["words"])
+    result = conn.llm.response_no_stream(conn.config["prompt"], wakeup_word)
+    tts_file = await asyncio.to_thread(conn.tts.to_tts, result)
+    if tts_file is not None and os.path.exists(tts_file):
+        file_type = os.path.splitext(tts_file)[1]
+        if file_type:
+            file_type = file_type.lstrip('.')
+        old_file = getWakeupWordFile("my_" +WAKEUP_CONFIG["file_name"])
+        if old_file is not None:
+            os.remove(old_file)
+        """将文件挪到"wakeup_words.mp3"""
+        shutil.move(tts_file, WAKEUP_CONFIG["dir"] + "my_" +WAKEUP_CONFIG["file_name"] + "." + file_type)
+        WAKEUP_CONFIG["create_time"] = time.time()

main/xiaozhi-server/core/handle/intentHandler.py

@@ -2,6 +2,7 @@ from config.logger import setup_logging
 import json
 import uuid
 from core.handle.sendAudioHandle import send_stt_message
+from core.handle.helloHandle import checkWakeupWords
 from core.utils.util import remove_punctuation_and_length
 
 TAG = __name__
@@ -12,6 +13,10 @@ async def handle_user_intent(conn, text):
     # 检查是否有明确的退出命令
     if await check_direct_exit(conn, text):
         return True
+    # 检查是否是唤醒词
+    if await checkWakeupWords(conn, text):
+        return True
+
     if conn.use_function_call_mode:
         # 使用支持function calling的聊天方法,不再进行意图分析
         return False
@@ -35,6 +40,7 @@ async def check_direct_exit(conn, text):
     return False
 
 
+
 async def analyze_intent_with_llm(conn, text):
     """使用LLM分析用户意图"""
     if not hasattr(conn, 'intent') or not conn.intent:

main/xiaozhi-server/core/handle/sendAudioHandle.py

@@ -7,12 +7,26 @@ from core.utils.util import remove_punctuation_and_length, get_string_no_punctua
 TAG = __name__
 logger = setup_logging()
 
+
 async def sendAudioMessage(conn, audios, text, text_index=0):
     # 发送句子开始消息
     if text_index == conn.tts_first_text_index:
         logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
     await send_tts_message(conn, "sentence_start", text)
 
+    # 播放音频
+    await sendAudio(conn, audios)
+
+    await send_tts_message(conn, "sentence_end", text)
+
+    # 发送结束消息（如果是最后一个文本）
+    if conn.llm_finish_task and text_index == conn.tts_last_text_index:
+        await send_tts_message(conn, 'stop', None)
+        if conn.close_after_chat:
+            await conn.close()
+
+# 播放音频
+async def sendAudio(conn, audios):
     # 流控参数优化
     frame_duration = 62  # 帧时长（毫秒），增加余量
     start_time = time.perf_counter()
@@ -46,13 +60,6 @@ async def sendAudioMessage(conn, audios, text, text_index=0):
         # 动态调整下次延迟，补偿发送耗时
         play_position += frame_duration  # 更新播放位置
 
-    await send_tts_message(conn, "sentence_end", text)
-
-    # 发送结束消息（如果是最后一个文本）
-    if conn.llm_finish_task and text_index == conn.tts_last_text_index:
-        await send_tts_message(conn, 'stop', None)
-        if conn.close_after_chat:
-            await conn.close()
 
 async def send_tts_message(conn, state, text=None):
     """发送 TTS 状态消息"""
@@ -64,10 +71,20 @@ async def send_tts_message(conn, state, text=None):
     if text is not None:
         message["text"] = text
 
-    await conn.websocket.send(json.dumps(message))
+    # TTS播放结束
     if state == "stop":
+        # 播放提示音
+        tts_notify = conn.config.get("enable_stop_tts_notify", False)
+        if tts_notify:
+            stop_tts_notify_voice = conn.config.get("stop_tts_notify_voice", "config/assets/tts_notify.mp3")
+            audios, duration = conn.tts.audio_to_opus_data(stop_tts_notify_voice)
+            await sendAudio(conn, audios)
+        # 清除服务端讲话状态
         conn.clearSpeakStatus()
 
+    # 发送消息到客户端
+    await conn.websocket.send(json.dumps(message))
+
 
 async def send_stt_message(conn, text):
     """发送 STT 状态消息"""

main/xiaozhi-server/core/handle/textHandle.py

@@ -2,7 +2,9 @@ from config.logger import setup_logging
 import json
 from core.handle.abortHandle import handleAbortMessage
 from core.handle.helloHandle import handleHelloMessage
+from core.utils.util import remove_punctuation_and_length
 from core.handle.receiveAudioHandle import startToChat, handleAudioMessage
+from core.handle.sendAudioHandle import send_stt_message, send_tts_message
 from core.handle.iotHandle import handleIotDescriptors, handleIotStatus
 
 TAG = __name__
@@ -38,7 +40,21 @@ async def handleTextMessage(conn, message):
                 conn.client_have_voice = False
                 conn.asr_audio.clear()
                 if "text" in msg_json:
-                    await startToChat(conn, msg_json["text"])
+                    text = msg_json["text"]
+                    _, text = remove_punctuation_and_length(text)
+
+                    # 识别是否是唤醒词
+                    is_wakeup_words = text in conn.config.get("wakeup_words")
+                    # 是否开启唤醒词回复
+                    enable_greeting = conn.config.get("enable_greeting", True)
+
+                    if is_wakeup_words and not enable_greeting:
+                        # 如果是唤醒词，且关闭了唤醒词回复，就不用回答
+                        await send_stt_message(conn, text)
+                        await send_tts_message(conn, "stop", None)
+                    else:
+                        # 否则需要LLM对文字内容进行答复
+                        await startToChat(conn, text)
         elif msg_json["type"] == "iot":
             if "descriptors" in msg_json:
                 await handleIotDescriptors(conn, msg_json["descriptors"])